A Kubernetes-native Go runtime for crash-resumable LLM workflows with event-sourced recovery, PostgreSQL leases and fencing tokens, and OpenTelemetry observability.
Concept artwork
A Go-based distributed agent runtime with event-sourced recovery and idempotent tool execution, so long-running LLM workflows resume after crashes without replaying completed side effects. A Kubernetes-native execution layer coordinates distributed workers with PostgreSQL leases and fencing tokens, and end-to-end OpenTelemetry + Prometheus observability covers every model and tool call.
Achievements
Engineered a Go-based distributed agent runtime with event-sourced recovery and idempotent tool execution, allowing long-running LLM workflows to resume after crashes without replaying completed side effects.
Built a Kubernetes-native execution layer with PostgreSQL leases and fencing tokens to coordinate distributed workers, handling pod failures, graceful shutdowns, and rolling updates while preserving single-writer execution.
Added end-to-end OpenTelemetry + Prometheus observability across model and tool calls, validating throughput, p95/p99 latency, and failure recovery through chaos and load testing.